Universal inference

• DOI: 10.1073/pnas.1922664117
• Publication Date: 2020-07-07T00:30:05Z
• Authors: Larry Wasserman; Aaditya Ramdas; Sivaraman Balakri...
• Keywords: Methodology (stat.ME); FOS: Computer and information sciences; Statistics - Machine Learning; FOS: Mathematics; Mathematics - Statistics Theory; Machine Learning (stat.ML); Statistics Theory (math.ST); 0101 mathematics; 16. Peace & justice; 01 natural sciences; Statistics - Methodology

Significance

Most statistical methods rely on certain mathematical conditions, known as regularity assumptions, to ensure their validity. Without these conditions, statistical quantities like P values and confidence intervals might not be valid. In this paper we give a surprisingly simple method for producing statistical significance statements without any regularity conditions. The resulting hypothesis tests can be used for any parametric model and for several nonparametric models.